A content provider specifies a content campaign along with a desired metric to achieve for the campaign, such as a budget. For each opportunity to present content to a user, an online publishing system selects content to a group of users using a selection process. To achieve the desired metric for the content campaign, the publishing system determines a probability of participating in the selection process with content from the content campaign based on feedback about the current performance of the campaign. For example, the system compares the opportunities passed and the budget spent for the content campaign to a current time and budget expenditure, and then it calculates an equilibrium probability that will achieve the desired budget at the end of the campaign. The system then determines whether to participate in a selection process for each new opportunity to present content using this adjusted equilibrium probability.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method executed by an online system, the method comprising: receiving, at the online system, a content campaign that includes a target budget and a duration for spending the target budget; determining a goal budget curve that relates a cumulative budget spent over time, where the budget curve reaches the target budget upon completion of the duration of the content campaign, the budget curve associated with an equilibrium probability of bidding for achieving the goal budget curve; receiving a plurality of opportunities to present content to a user of the online system; selecting a subset of the opportunities at a rate according to the equilibrium probability; for each of the selected opportunities, participating in a selection process with content from the content campaign, where the selection process determines a content item to provide in response to the opportunity to present content to a user of the online system; determining a plurality of periods during the duration of the content campaign; and for each of the plurality of periods: determining a number of effective opportunities that have passed during the previous periods of the content campaign; determining a desired budget spent over the previous periods of the content campaign according to the budget curve; determining an actual amount of the budget spent during the previous periods of the content campaign; determining a difference between the desired budget spent and the actual budget spent during the previous periods of the content campaign; adjusting the equilibrium probability based on the determined difference; and determining, during the period, whether to participate in each of a plurality of opportunities to select content for one or more users of an online system at a rate according to the adjusted equilibrium probability.
2. The method of claim 1 , wherein the adjusted equilibrium probability is determined using a ratio of the effective opportunities passed and the actual budget spent for the previous periods.
3. The method of claim 1 , wherein the number of effective opportunities passed is determined using a ratio of a number of opportunities associated with the content campaign during the period and an estimated total number of opportunities for the duration of the campaign.
4. The method of claim 1 , wherein a bid amount associated with content in the content campaign is adjusted based at least in part on the budget of the content campaign and the duration of the content campaign, the bid amount adjusted at a lower frequency than the equilibrium probability.
5. The method of claim 1 , wherein determining a probability adjustment further comprises: identifying a point on the budget curve at a future time within the duration of the content campaign; determining a probability adjustment, the probability adjustment determined to intersect the identified point on the budget curve.
6. The method of claim 1 , wherein responsive to the budget of the content campaign being modified during the duration of the content campaign, the calculated equilibrium probability is adjusted by a scaling factor.
7. The method of claim 6 , wherein the scaling factor is less than the inverse of the equilibrium probability.
8. The method of claim 1 , wherein the estimated equilibrium probability represents a spending rate that approximates the slope of the budget curve.
9. The method of claim 1 , wherein adjusting the estimated equilibrium probability is performed iteratively during the duration of the content campaign.
10. A non-transitory computer-readable storage medium storing computer program instructions executable by a processor to perform operations comprising: receiving, at an online system, a content campaign that includes a target budget and a duration for spending the target budget; determining a goal budget curve that relates a cumulative budget spent over time, where the budget curve reaches the target budget upon completion of the duration of the content campaign, the budget curve associated with an equilibrium probability of bidding for achieving the goal budget curve; receiving a plurality of opportunities to present content to a user of the online system; selecting a subset of the opportunities at a rate according to the equilibrium probability; for each of the selected opportunities, participating in a selection process with content from the content campaign, where the selection process determines a content item to provide in response to the opportunity to present content to a user of the online system; determining a plurality of periods during the duration of the content campaign; and for each of the plurality of periods: determining a number of effective opportunities that have passed during the previous periods of the content campaign; determining a desired budget spent over the previous periods of the content campaign according to the budget curve; determining an actual amount of the budget spent during the previous periods of the content campaign; determining a difference between the desired budget spent and the actual budget spent during the previous periods of the content campaign; adjusting the equilibrium probability based on the determined difference; and determining, during the period, whether to participate in each of a plurality of opportunities to select content for one or more users of an online system at a rate according to the adjusted equilibrium probability.
11. The computer-readable storage medium of claim 10 , wherein the adjusted equilibrium probability is determined using a ratio of the effective opportunities passed and the actual budget spent for the previous periods.
12. The computer-readable storage medium of claim 10 , wherein the number of effective opportunities passed is determined using a ratio of a number of opportunities associated with the content campaign during the period and an estimated total number of opportunities for the duration of the campaign.
13. The computer-readable storage medium of claim 10 , wherein a bid amount associated with content in the content campaign is adjusted based at least in part on the budget of the content campaign and the duration of the content campaign, the bid amount adjusted at a lower frequency than the equilibrium probability.
14. The computer-readable storage medium of claim 10 , wherein determining a probability adjustment further comprises: identifying a point on the budget curve at a future time within the duration of the content campaign; determining a probability adjustment, the probability adjustment determined to intersect the identified point on the budget curve.
15. The computer-readable storage medium of claim 10 , wherein responsive to the budget of the content campaign being modified during the duration of the content campaign, the calculated equilibrium probability is adjusted by a scaling factor.
16. The computer-readable storage medium of claim 15 , wherein the scaling factor is less than the inverse of the equilibrium probability.
17. The computer-readable storage medium of claim 10 , wherein the estimated equilibrium probability represents a spending rate that approximates the slope of the budget curve.
18. The computer-readable storage medium of claim 10 , wherein adjusting the estimated equilibrium probability is performed iteratively during the duration of the content campaign.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
April 1, 2018
December 29, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.